masster 0.5.4__py3-none-any.whl → 0.5.5__py3-none-any.whl

masster/sample/save.py

@@ -411,6 +411,11 @@ def export_mgf(
             rt_str = f"{rt:.2f}"
             mz_str = f"{mz:.4f}"
 
+            # Initialize charge for this feature
+            charge = preferred_charge
+            if row["charge"] is not None and row["charge"] != 0:
+                charge = row["charge"]
+
             # Skip features without MS2 data (unless include_all_ms1 is True, but we already handled MS1 above)
             if row["ms2_scans"] is None:
                 skip = skip + 1

masster/study/helpers.py

@@ -500,7 +500,7 @@ def align_reset(self):
 # TODO I don't get this param
 def get_consensus(self, quant="chrom_area"):
     if self.consensus_df is None:
-        self.logger.error("No consensus map found.")
+        self.logger.error("No consensus found.")
         return None
 
     # Convert Polars DataFrame to pandas for this operation since the result is used for export
@@ -613,7 +613,7 @@ def get_gaps_matrix(self, uids=None, samples=None):
     import polars as pl
     
     if self.consensus_df is None or self.consensus_df.is_empty():
-        self.logger.error("No consensus map found.")
+        self.logger.error("No consensus found.")
         return None
     
     if self.consensus_mapping_df is None or self.consensus_mapping_df.is_empty():

masster/study/plot.py

@@ -564,6 +564,10 @@ def plot_consensus_2d(
     Parameters:
         filename (str, optional): Path to save the plot
         colorby (str): Column name to use for color mapping (default: "number_samples")
+                      Automatically detects if column contains categorical (string) or 
+                      numeric data and applies appropriate color mapping:
+                      - Categorical: Uses factor_cmap with distinct colors and legend
+                      - Numeric: Uses LinearColorMapper with continuous colorbar
         sizeby (str): Column name to use for size mapping (default: "inty_mean")
         markersize (int): Base marker size (default: 6)
         scaling (str): Controls whether points scale with zoom. Options:
@@ -645,12 +649,13 @@ def plot_consensus_2d(
     from bokeh.models import HoverTool
     from bokeh.models import LinearColorMapper
     from bokeh.io.export import export_png
+    from bokeh.transform import factor_cmap
 
     try:
         from bokeh.models import ColorBar  # type: ignore[attr-defined]
     except ImportError:
         from bokeh.models.annotations import ColorBar
-    from bokeh.palettes import viridis
+    from bokeh.palettes import viridis, Category20
 
     # Import cmap for colormap handling
     from cmap import Colormap
@@ -695,61 +700,144 @@ def plot_consensus_2d(
         self.logger.warning(f"Could not interpret colormap '{cmap}': {e}, falling back to viridis")
         palette = viridis(256)
 
-    color_mapper = LinearColorMapper(
-        palette=palette,
-        low=data[colorby].min(),
-        high=data[colorby].max(),
+    # Check if colorby column contains categorical data (string/object)
+    colorby_values = data[colorby].to_list()
+    is_categorical = (
+        data_pd[colorby].dtype in ["object", "string", "category"] or
+        isinstance(colorby_values[0], str) if colorby_values else False
     )
+    
+    if is_categorical:
+        # Handle categorical coloring
+        # Use natural order of unique values - don't sort to preserve correct legend mapping
+        # Sorting would break the correspondence between legend labels and point colors
+        unique_values = [v for v in data_pd[colorby].unique() if v is not None]
+        
+        if len(unique_values) <= 20:
+            palette = Category20[min(20, max(3, len(unique_values)))]
+        else:
+            # For many categories, use a subset of the viridis palette
+            palette = viridis(min(256, len(unique_values)))
+        
+        color_mapper = factor_cmap(colorby, palette, unique_values)
+    else:
+        # Handle numeric coloring with LinearColorMapper
+        color_mapper = LinearColorMapper(
+            palette=palette,
+            low=data[colorby].min(),
+            high=data[colorby].max(),
+        )
     # scatter plot rt vs mz
     p = bp.figure(
         width=width,
         height=height,
-        title="Consensus map",
+        title=f"Consensus features, colored by {colorby}",
     )
-    p.xaxis.axis_label = "Retention Time (min)"
-    p.yaxis.axis_label = "m/z"
+    p.xaxis.axis_label = "RT [s]"
+    p.yaxis.axis_label = "m/z [Th]"
     scatter_renderer: Any = None
-    if scaling.lower() in ["dyn", "dynamic"]:
-        # Calculate appropriate radius for dynamic scaling based on data range
-        rt_range = data["rt"].max() - data["rt"].min()
-        mz_range = data["mz"].max() - data["mz"].min()
-        # Use a fraction of the smaller dimension for radius, similar to sample plotting
-        dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+    if is_categorical:
+        # For categorical data, create separate renderers for each category
+        # This enables proper legend interactivity where each category can be toggled independently
+        unique_values = [v for v in data_pd[colorby].unique() if v is not None]
+        
+        if len(unique_values) <= 20:
+            palette = Category20[min(20, max(3, len(unique_values)))]
+        else:
+            palette = viridis(min(256, len(unique_values)))
+        
+        # Create a separate renderer for each category
+        for i, category in enumerate(unique_values):
+            # Filter data for this category
+            category_data = data.filter(pl.col(colorby) == category)
+            category_data_pd = category_data.to_pandas()
+            category_source = bp.ColumnDataSource(category_data_pd)
+            
+            color = palette[i % len(palette)]
+            
+            if scaling.lower() in ["dyn", "dynamic"]:
+                # Calculate appropriate radius for dynamic scaling
+                rt_range = data["rt"].max() - data["rt"].min()
+                mz_range = data["mz"].max() - data["mz"].min()
+                dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+                
+                renderer = p.circle(
+                    x="rt",
+                    y="mz", 
+                    radius=dynamic_radius,
+                    fill_color=color,
+                    line_color=None,
+                    alpha=alpha,
+                    source=category_source,
+                    legend_label=str(category),
+                )
+            else:
+                renderer = p.scatter(
+                    x="rt",
+                    y="mz",
+                    size="markersize", 
+                    fill_color=color,
+                    line_color=None,
+                    alpha=alpha,
+                    source=category_source,
+                    legend_label=str(category),
+                )
+        
+        # No single scatter_renderer for categorical data
+        scatter_renderer = None
         
-        scatter_renderer = p.circle(
-            x="rt",
-            y="mz",
-            radius=dynamic_radius,
-            fill_color={"field": colorby, "transform": color_mapper},
-            line_color=None,
-            alpha=alpha,
-            source=source,
-        )
     else:
-        scatter_renderer = p.scatter(
-            x="rt",
-            y="mz",
-            size="markersize",
-            fill_color={"field": colorby, "transform": color_mapper},
-            line_color=None,
-            alpha=alpha,
-            source=source,
-        )
+        # Handle numeric coloring - single renderer with color mapping
+        if scaling.lower() in ["dyn", "dynamic"]:
+            # Calculate appropriate radius for dynamic scaling
+            rt_range = data["rt"].max() - data["rt"].min()
+            mz_range = data["mz"].max() - data["mz"].min()
+            dynamic_radius = min(rt_range, mz_range) * 0.0005 * markersize
+            
+            scatter_renderer = p.circle(
+                x="rt",
+                y="mz",
+                radius=dynamic_radius,
+                fill_color={"field": colorby, "transform": color_mapper},
+                line_color=None,
+                alpha=alpha,
+                source=source,
+            )
+        else:
+            scatter_renderer = p.scatter(
+                x="rt",
+                y="mz",
+                size="markersize",
+                fill_color={"field": colorby, "transform": color_mapper},
+                line_color=None,
+                alpha=alpha,
+                source=source,
+            )
     # add hover tool
-    # Start with base tooltips
+    # Start with base tooltips - rt and mz moved to top, removed consensus_id and iso_mean
     tooltips = [
+        ("rt", "@rt"),
+        ("mz", "@mz"),
         ("consensus_uid", "@consensus_uid"),
-        ("consensus_id", "@consensus_id"),
         ("number_samples", "@number_samples"),
         ("number_ms2", "@number_ms2"),
-        ("rt", "@rt"),
-        ("mz", "@mz"),
         ("inty_mean", "@inty_mean"),
-        ("iso_mean", "@iso_mean"),
         ("coherence_mean", "@chrom_coherence_mean"),
         ("prominence_scaled_mean", "@chrom_prominence_scaled_mean"),
     ]
     
+    # Add adduct_top if it exists in data
+    if "adduct_top" in data.columns:
+        tooltips.append(("adduct_top", "@adduct_top"))
+    
+    # Add id_top_name if it exists in data
+    if "id_top_name" in data.columns:
+        tooltips.append(("id_top_name", "@id_top_name"))
+    
+    # Add id_top_adduct if it exists in data
+    if "id_top_adduct" in data.columns:
+        tooltips.append(("id_top_adduct", "@id_top_adduct"))
+    
     # Add id_top_* columns if they exist and have non-null values
     id_top_columns = ["id_top_name", "id_top_class", "id_top_adduct", "id_top_score"]
     for col in id_top_columns:
@@ -764,19 +852,28 @@ def plot_consensus_2d(
     
     hover = HoverTool(
         tooltips=tooltips,
-        renderers=[scatter_renderer],
     )
+    # For categorical data, hover will work on all renderers automatically
+    # For numeric data, specify the single renderer
+    if not is_categorical and scatter_renderer:
+        hover.renderers = [scatter_renderer]
+    
     p.add_tools(hover)
 
-    # add colorbar
-    color_bar = ColorBar(
-        color_mapper=color_mapper,
-        label_standoff=12,
-        location=(0, 0),
-        title=colorby,
-        ticker=BasicTicker(desired_num_ticks=8),
-    )
-    p.add_layout(color_bar, "right")
+    # add colorbar only for numeric data (LinearColorMapper)
+    if not is_categorical:
+        color_bar = ColorBar(
+            color_mapper=color_mapper,
+            label_standoff=12,
+            location=(0, 0),
+            title=colorby,
+            ticker=BasicTicker(desired_num_ticks=8),
+        )
+        p.add_layout(color_bar, "right")
+    else:
+        # For categorical data, configure the legend that was automatically created
+        p.legend.location = "top_right"
+        p.legend.click_policy = "hide"
 
     if filename is not None:
         # Convert relative paths to absolute paths using study folder as base

masster/study/processing.py

@@ -341,9 +341,6 @@ def _integrate_chrom_impl(self, **kwargs):
     uids = params.get("uids")
     rt_tol = params.get("rt_tol")
 
-    if self.consensus_map is None:
-        self.logger.error("No consensus map found.")
-        return
     if uids is None:
         # get all consensus_id from consensus_df
         ids = self.consensus_df["consensus_uid"].to_list()

masster/wizard/wizard.py

@@ -455,6 +455,9 @@ class Wizard:
         params_lines.append('    # === Processing Parameters ===')
         params_lines.append(f'    "adducts": {params_dict.get("adducts", [])!r},  # Adduct specifications for feature detection and annotation')
         params_lines.append(f'    "detector_type": {params_dict.get("detector_type", "unknown")!r},  # MS detector type ("orbitrap", "tof", "unknown")')
+        params_lines.append(f'    "noise": {params_dict.get("noise", 50.0)},  # Noise threshold for feature detection')
+        params_lines.append(f'    "chrom_fwhm": {params_dict.get("chrom_fwhm", 0.5)},  # Chromatographic peak full width at half maximum (seconds)')
+        params_lines.append(f'    "chrom_peak_snr": {params_dict.get("chrom_peak_snr", 5.0)},  # Minimum signal-to-noise ratio for chromatographic peaks')
         params_lines.append('')
         
         # Alignment & Merging
@@ -643,6 +646,7 @@ class Wizard:
             '        # Step 4: Add sample5 files to study',
             '        print("\\nStep 4/7: Adding samples to study...")',
             '        study.add(str(Path(PARAMS[\'folder\']) / "*.sample5"))',
+            '        study.features_filter(study.features_select(chrom_coherence=0.1, chrom_prominence_scaled=1))',
             '        ',
             '        # Step 5: Core processing',
             '        print("\\nStep 5/7: Processing...")',
@@ -651,29 +655,14 @@ class Wizard:
             '            rt_tol=PARAMS[\'rt_tol\']',
             '        )',
             '        ',
-            '        # Merge and create consensus features',
-            '        # Use optimized method for large datasets (>500 samples)',
-            '        num_samples = len(study.samples)',
-            '        if num_samples > 500:',
-            '            print(f"  Large dataset detected ({num_samples} samples), using optimized qt_chunked + hierarchical method")',
-            '            study.merge(',
-            '                method="qt_chunked",',
-            '                dechunking="hierarchical",', 
-            '                min_samples=PARAMS[\'min_samples_per_feature\'],',
-            '                threads=PARAMS[\'num_cores\'],',
-            '                rt_tol=PARAMS[\'rt_tol\'],',
-            '                mz_tol=PARAMS[\'mz_tol\']',
-            '            )',
-            '        else:',
-            '            print(f"  Using standard merge method for {num_samples} samples")',
-            '            study.merge(',
-            '                min_samples=PARAMS[\'min_samples_per_feature\'],',
-            '                threads=PARAMS[\'num_cores\'],',
-            '                rt_tol=PARAMS[\'rt_tol\'],',
-            '                mz_tol=PARAMS[\'mz_tol\']',
-            '            )',
+            '        study.merge(',
+            '            method="qt",',
+            '            min_samples=PARAMS[\'min_samples_per_feature\'],',
+            '            threads=PARAMS[\'num_cores\'],',
+            '            rt_tol=PARAMS[\'rt_tol\'],'
+            '        )',
             '        study.find_iso()',
-            '        study.fill(min_samples_rel=0.0)',
+            '        study.fill()',
             '        study.integrate()',    
             '        ',
             '        # Step 6/7: Saving results',
@@ -689,8 +678,8 @@ class Wizard:
             '        study.plot_consensus_2d(filename="consensus.png")',
             '        study.plot_alignment(filename="alignment.html")',
             '        study.plot_alignment(filename="alignment.png")',
-            '        study.plot_pca(filename="pca.html")',
-            '        study.plot_pca(filename="pca.png")',
+            '        study.plot_samples_pca(filename="pca.html")',
+            '        study.plot_samples_pca(filename="pca.png")',
             '        study.plot_bpc(filename="bpc.html")',
             '        study.plot_bpc(filename="bpc.png")',
             '        study.plot_rt_correction(filename="rt_correction.html")',

{masster-0.5.4.dist-info → masster-0.5.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.4
+Version: 0.5.5
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.5.4.dist-info → masster-0.5.5.dist-info}/RECORD

@@ -29,7 +29,7 @@ masster/sample/processing.py,sha256=CjaLCElDKECeCvYWqzT5EH_-rPQ0Y4A30zKjZfqmS5s,
 masster/sample/quant.py,sha256=tHNjvUFTdehKR31BXBZnVsBxMD9XJHgaltITOjr71uE,7562
 masster/sample/sample.py,sha256=O2PY7DnRx7VkASBU4qKQcTqND1aRfd0OCjKK9Rjn5uw,20574
 masster/sample/sample5_schema.json,sha256=H5e2T6rHIDzul2kp_yP-ILUUWUpW08wP2pEQjMR0nSk,3977
-masster/sample/save.py,sha256=2yQtcQcRJjgAKPImTydj7LpyyMop_Q9JKRlNEK4yU6k,36339
+masster/sample/save.py,sha256=q1DjzVCB2FsTi9Sk-szd2-Nr7kPbqqFhJpjAWNfSCno,36536
 masster/sample/sciex.py,sha256=vnbxsq_qnAQVuzcpziP1o3IC4kM5amGBcPmC2TAuDLw,46319
 masster/sample/defaults/__init__.py,sha256=A09AOP44cxD_oYohyt7XFUho0zndRcrzVD4DUaGnKH4,447
 masster/sample/defaults/find_adducts_def.py,sha256=Bu2KiBJRxD0SAnOPNMm_Nk-6fx6QYoRXjFNGzz-0_o0,13570
@@ -41,13 +41,13 @@ masster/study/__init__.py,sha256=55axdFuqRX4aXtJ8ocnhcLB32fNtmmJpCi58moO0r4g,237
 masster/study/analysis.py,sha256=L-wXBnGZCLB5UUDrjIdOiMG9zdej3Tw_SftcEmmTukM,84264
 masster/study/export.py,sha256=joFK9jip2UM4lVAvhkdKVeUdNdM4D8uP2WE49IaVJgw,60172
 masster/study/h5.py,sha256=84plxM7gYFdn_mNbcg8XxE_NRZmiIBqs_XhfHMiXshk,95364
-masster/study/helpers.py,sha256=s5jLUmxDAs_Qn6dVwpkwlwuwliMDEBjmeikS6OrxdSE,183137
+masster/study/helpers.py,sha256=ZhvLetoEROHMSrMKZo8jXQMJhTochITgAG_vwjs_8Mg,183129
 masster/study/id.py,sha256=r_vZQYNxqNXf_pjgk_CLkl1doLnLa956mTuVmlHN52o,80075
 masster/study/load.py,sha256=7d11294YYEGrSKox3cwvetv2vqcstYT1SnyAhHH5V_Q,107706
 masster/study/merge.py,sha256=D9xNRlEaMPTPZQAZhiBBSzQ-27lD60fCDmKb0cYST-M,149764
 masster/study/parameters.py,sha256=bTvmcwX9INxzcrEAmTiFH8qeWVhwkvMTZjuP394pz5o,3279
-masster/study/plot.py,sha256=wg2X3P-0J6mW0N0dJS0dX6KLGtt9mXj6w1j3E9nvlvo,103086
-masster/study/processing.py,sha256=O6X7wgeq0kXSyMO12g23cqB8cYO60gLRMxuJC2uhSMY,58644
+masster/study/plot.py,sha256=LEIzoYiUyq1aswh-sw8S-ESvN2DaQKN5l22yLW8gZe8,107647
+masster/study/processing.py,sha256=n5208v-JQGq3bBP-ncgl2__hHWSQQYHx2fl4Mm0THdI,58538
 masster/study/save.py,sha256=47AP518epJJ9TjaGGyrLKsMsyjIk8_J4ka7bmsnRtFQ,9268
 masster/study/study.py,sha256=TnZkTLB8Z5R-AVqoHfUNvmkTthfUI4OPmBo_LYR_e8g,38654
 masster/study/study5_schema.json,sha256=0IZxM9VVI0TUlx74BPzJDT44kySi6NZZ6iLR0j8bU_s,7736
@@ -65,9 +65,9 @@ masster/study/defaults/study_def.py,sha256=h8dYbi9xv0sesCSQik49Z53IkskMmNtW6ixl7
 masster/wizard/README.md,sha256=mL1A3YWJZOefpJ6D0-HqGLkVRmUlOpwyVFdvJBeeoZM,14149
 masster/wizard/__init__.py,sha256=a2hcZnHASjfuw1lqZhZnvTR58rc33rRnoGAY_JfvGhI,683
 masster/wizard/example.py,sha256=xEZFTH9UZ8HKOm6s3JL8Js0Uw5ChnISWBHSZCL32vsM,7983
-masster/wizard/wizard.py,sha256=6VqeOyKJ-9n0376CVbNuQo4vKLFjE0Sl2KexWZclQew,38580
-masster-0.5.4.dist-info/METADATA,sha256=wjgydggoAm3JBUOi0PrJ1oPUgUTvB3qKZ1MorC8NBOE,45113
-masster-0.5.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-masster-0.5.4.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
-masster-0.5.4.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
-masster-0.5.4.dist-info/RECORD,,
+masster/wizard/wizard.py,sha256=UobIGFZtp1s_9WJlpl6DQ2-pp7flPQ6dlYZJqYE92OM,38131
+masster-0.5.5.dist-info/METADATA,sha256=ALpQYEYxgqYZ0XGZjcdXvgkEE_AKC0-KqepR1fwQ3hc,45113
+masster-0.5.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+masster-0.5.5.dist-info/entry_points.txt,sha256=ZHguQ_vPmdbpqq2uGtmEOLJfgP-DQ1T0c07Lxh30wc8,58
+masster-0.5.5.dist-info/licenses/LICENSE,sha256=bx5iLIKjgAdYQ7sISn7DsfHRKkoCUm1154sJJKhgqnU,35184
+masster-0.5.5.dist-info/RECORD,,